您的位置:首页  > 论文页面

基于神经网络的模拟PCB诊断方法及其智能测试系统的研究

发表时间:2011-02-28  浏览量:1533  下载量:793
全部作者: 祝文姬,何怡刚
作者单位: 湖南大学电气与信息工程学院
摘 要: 提出一种小波变换、遗传算法与神经网络相结合的模拟印刷电路板(printed circuit board,PCB)测试新方法及其软硬件的实现。这种测试方法使用小波作为消噪工具,对信号进行消噪和小波多尺度分解,进行归一化处理后提取故障特征信息作为神经网络的输入样本。而为解决误差反向传播(back propagation,BP)网络权值随机初始化带来的问题,用遗传算法优化BP网络的结构和初始权值分布。在充分考虑PCB自动测试特点的基础上,提出基于数字信号处理(digital signal processing,DSP)控制的PCB测试系统。研究其故障特征提取、样本选择、诊断系统结构及其软硬件实现方法,并通过电路诊断实例,阐述该方法的具体实现方式,验证所提方法的鲁棒性。
关 键 词: 电路与系统;误差反向传播网络;印刷电路板测试系统;数字信号处理;小波变换;遗传算法
Title: Study on analog PCB diagnosis method based on neural network and its intelligent testing system
Author: ZHU Wenji, HE Yigang
Organization: College of Electrical and Information Engineering, Hunan Universit
Abstract: Based on wavelet decomposition, genetic algorithm (GA) and neural networks (NNs), a new testing system for printed circuit board (PCB) is proposed. The proposed method is based on wavelet transformation that allows using the wavelet decomposition as a de-noise tool, the feature information is extracted by wavelet de-noising, multi-resolution, orthogonalization and normalization. And the input patterns are satisfied when the feature information applied to the neural networks. The proposed approach selects GA to optimize the structure and original weight distribution of BP networks. Under considering the characteristics of the printed circuit board, the controlled PCB testing system based on digital signal processing (DSP) is performed. Finally, the realization of the proposed strategy is expounded by using a practical circuit.
Key words: circuits and systems; back propagation network; printed circuit board testing system; digital signal processing; wavelet transformation; genetic algorithm
发表期数: 2011年2月第4期
引用格式: 祝文姬,何怡刚. 基于神经网络的模拟PCB诊断方法及其智能测试系统的研究[J]. 中国科技论文在线精品论文,2011,4(4):349-357.
 
0 评论数 0
暂无评论
友情链接